© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160985
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    1.52
    다
    1.48
    ে
    1.48
    in
    1.38
    ४
    1.34
    した
    1.30
    ל
    1.27
    3
    1.26
    at
    1.25
    して
    1.23
    POSITIVE LOGITS
    ק
    1.41
    1.21
    к
    1.05
     you
    1.04
    isation
    1.00
     is
    0.99
     refriger
    0.98
    \
    0.96
     malignancy
    0.93
     quatern
    0.88
    Activations Density 0.000%

    No Known Activations